image

Name: image
Author: axoviq-ai

681stars61forks

How to install image?

axoviq-ai/synthadoc/image

$npx -y skills add axoviq-ai/synthadoc --skill image

Installs into the current project.

Summary

Extract text from images using a vision LLM

Files · 1

View on GitHub

SKILL.md

1	# Image Skill
2
3	Base64-encodes the image and passes it to a vision-capable LLM that extracts
4	all text and key information. Returns the LLM's response as `result.text`.
5
6	## Setup
7
8	No pip dependency — the skill uses only the Python standard library plus a
9	LLM provider you supply at construction time. The provider can be any object
10	that implements the `complete()` interface (see below).
11
12	## Standalone usage
13
14	```python
15	import asyncio
16	from synthadoc.skills.image.scripts.main import ImageSkill
17
18	# ImageSkill REQUIRES a vision-capable provider — calling extract() without
19	# one raises ValueError immediately.
20	skill = ImageSkill(provider=my_provider)
21
22	async def main():
23	result = await skill.extract("/path/to/screenshot.png")
24	print(result.text) # extracted text from the image
25	print(result.metadata) # {"tokens_input": N, "tokens_output": N}
26
27	asyncio.run(main())
28	```
29
30	Provider interface — any object with this async method:
31
32	```python
33	async def complete(
34	messages: list, # list of Message objects from synthadoc.skills.base
35	system: str \| None = None,
36	temperature: float = 0.0,
37	max_tokens: int = 4096,
38	) -> object # must have .text (str), .input_tokens (int), .output_tokens (int)
39	```
40
41	Build the provider with any vision-capable model. `Message` is importable
42	from `synthadoc.skills.base` — no dependency on `synthadoc.providers`:
43
44	```python
45	from synthadoc.skills.base import Message
46	```
47
48	Supported image formats: `.png`, `.jpg`/`.jpeg`, `.webp`, `.gif`, `.tiff`
49
50	## When this skill is used
51
52	- Source path ends with `.png`, `.jpg`, `.jpeg`, `.webp`, `.gif`, or `.tiff`
53	- User intent contains: `image`, `screenshot`, `diagram`, `photo`

People who liked this also viewed

6 picks

Type

ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026292k642
imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026165k66k
hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026145k37k
media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026144k37k
general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026124k37k
product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026121k37k

image

681stars61forks

View on GitHub

How to install image?

axoviq-ai/synthadoc/image

$npx -y skills add axoviq-ai/synthadoc --skill image

Installs into the current project.

Summary

Extract text from images using a vision LLM

Files · 1

View on GitHub

SKILL.md

1	# Image Skill
2
3	Base64-encodes the image and passes it to a vision-capable LLM that extracts
4	all text and key information. Returns the LLM's response as `result.text`.
5
6	## Setup
7
8	No pip dependency — the skill uses only the Python standard library plus a
9	LLM provider you supply at construction time. The provider can be any object
10	that implements the `complete()` interface (see below).
11
12	## Standalone usage
13
14	```python
15	import asyncio
16	from synthadoc.skills.image.scripts.main import ImageSkill
17
18	# ImageSkill REQUIRES a vision-capable provider — calling extract() without
19	# one raises ValueError immediately.
20	skill = ImageSkill(provider=my_provider)
21
22	async def main():
23	result = await skill.extract("/path/to/screenshot.png")
24	print(result.text) # extracted text from the image
25	print(result.metadata) # {"tokens_input": N, "tokens_output": N}
26
27	asyncio.run(main())
28	```
29
30	Provider interface — any object with this async method:
31
32	```python
33	async def complete(
34	messages: list, # list of Message objects from synthadoc.skills.base
35	system: str \| None = None,
36	temperature: float = 0.0,
37	max_tokens: int = 4096,
38	) -> object # must have .text (str), .input_tokens (int), .output_tokens (int)
39	```
40
41	Build the provider with any vision-capable model. `Message` is importable
42	from `synthadoc.skills.base` — no dependency on `synthadoc.providers`:
43
44	```python
45	from synthadoc.skills.base import Message
46	```
47
48	Supported image formats: `.png`, `.jpg`/`.jpeg`, `.webp`, `.gif`, `.tiff`
49
50	## When this skill is used
51
52	- Source path ends with `.png`, `.jpg`, `.jpeg`, `.webp`, `.gif`, or `.tiff`
53	- User intent contains: `image`, `screenshot`, `diagram`, `photo`

People who liked this also viewed

6 picks

Type